JigSync: Gauge-Resolved Synchronization for Jigsaw Reassembly under Unknown Piece Orientation
cs.CV
Submitted: 2026-09-16
Updated: 2026-09-16
Project page: https://sohamrsch.github.io/jigsync
License: http://creativecommons.org/licenses/by/4.0/
The gist: Square jigsaw reassembly requires recovering the spatial arrangement of shuffled fragments from their visual content and pairwise relationships.
Terminology
Abstract
Square jigsaw reassembly requires recovering the spatial arrangement of shuffled fragments from their visual content and pairwise relationships. While recent studies have made substantial progress, existing benchmarks typically assume that all fragments are provided upright, reducing reassembly to a permutation problem. We study the generalized problem in which each fragment may also have gone through an unknown rotation. For this setting we establish a gauge-unobservability theorem: the minimum of the weighted least-squares objective is exactly invariant under a uniform global rotation of arbitrary magnitude, so no residual-based criterion can recover the global orientation. The theorem further identifies how the issue of global orientation can be resolved: an orientation anchor estimated from the content of a single fragment, lying outside its scope, suffices. To address the above, we propose JigSync, which attains 63.8% and 31.8% absolute accuracy (AA) on GAP-3 and GAP-5, respectively, the highest reported on both, while additionally recovering a rotation per piece that neither benchmark requires. We release JigSync, a degradation protocol that sweeps shape, erosion, photometry, grid size, and rotation independently.
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- TEN: Twin Embedding Networks for the Jigsaw Puzzle Problem with Eroded Boundaries
- Pairwise Alignment & Compatibility for Arbitrarily Irregular Image Fragments
- Multi-Phase Relaxation Labeling for Square Jigsaw Puzzle Solving
- Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
- Solving Jigsaw Puzzles with Linear Programming
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models